metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_13_0
metrics:
- wer
model-index:
- name: openai/whisper-small
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_13_0
type: common_voice_13_0
config: eu
split: test
args: eu
metrics:
- name: Wer
type: wer
value: 18.83024828871157
openai/whisper-small
This model is a fine-tuned version of openai/whisper-small on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3914
- Wer: 18.8302
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1413 | 2.04 | 1000 | 0.3178 | 22.0139 |
| 0.0181 | 4.07 | 2000 | 0.3376 | 20.2864 |
| 0.0044 | 7.02 | 3000 | 0.3603 | 18.8768 |
| 0.0016 | 9.06 | 4000 | 0.3812 | 18.7756 |
| 0.0012 | 12.01 | 5000 | 0.3914 | 18.8302 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2